© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93786
    Prev
    Next
    INDEX
    Explanations

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AH
    -0.88
    AH
    -0.88
    ah
    -0.83
    ahs
    -0.80
     es
    -0.60
    formik
    -0.59
    DebuggerNonUser
    -0.58
     and
    -0.58
     O
    -0.56
     me
    -0.54
    POSITIVE LOGITS
     myſelf
    1.04
     itſelf
    1.02
     raiſ
    1.00
     Anſ
    0.98
     ſche
    0.95
     themſelves
    0.94
     ſmall
    0.94
     Theſe
    0.94
     pleaſure
    0.93
     doubtnut
    0.91
    Activations Density 0.033%

    No Known Activations