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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38813
    Prev
    Next
    INDEX
    Explanations

    subjective experiences

    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
     their
    -0.87
     they
    -0.75
     that
    -0.74
     like
    -0.65
     kanilang
    -0.64
     you
    -0.63
     Their
    -0.60
     made
    -0.60
     eorum
    -0.55
     opérés
    -0.55
    POSITIVE LOGITS
     فريبيس
    0.68
     Италијани
    0.68
     Vikipedi
    0.60
    ItemBackground
    0.59
     ghe
    0.54
    tvguidetime
    0.53
    AutoresizingMask
    0.53
     forgive
    0.52
     passim
    0.52
    EndProject
    0.51
    Activations Density 0.037%

    No Known Activations