© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 192
    Prev
    Next
    INDEX
    Explanations

    instances of the word "following", "follows", or "adherence", especially as it relates to instructions or subsequent events

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hdashline
    -1.13
     оригіналу
    -1.07
     المعيارى
    -0.94
     AttributeSet
    -0.91
    styleable
    -0.90
    zzleHttp
    -0.90
    ThroughAttribute
    -0.84
     cât
    -0.81
    Kaynakça
    -0.80
    KommentareTeilen
    -0.80
    POSITIVE LOGITS
     following
    2.73
    following
    2.63
     follows
    2.56
     Following
    2.55
     follow
    2.52
    Following
    2.47
    follow
    2.38
     FOLLOWING
    2.22
     Follows
    2.22
    follows
    2.20
    Activations Density 1.366%

    No Known Activations