© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4452
    Prev
    Next
    INDEX
    Explanations

    use

    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
     <<<<<<<<<<<<<<
    -0.82
    theless
    -0.71
    RenderAtEndOf
    -0.68
     препратки
    -0.68
    .)}
    -0.62
    Cyfeiriadau
    -0.60
    kloped
    -0.60
    adaş
    -0.60
     ProtoMessage
    -0.58
    ."]
    -0.56
    POSITIVE LOGITS
     some
    0.60
     a
    0.55
     bantuan
    0.48
     an
    0.45
     another
    0.45
     Need
    0.44
    Need
    0.44
    шек
    0.44
    ISupport
    0.44
    见
    0.41
    Activations Density 0.007%

    No Known Activations