© 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. 4449
    Prev
    Next
    INDEX
    Explanations

    time periods

    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
     initComponents
    -0.56
    allo
    -0.55
     or
    -0.54
    tagext
    -0.54
     Clemens
    -0.53
    Papier
    -0.52
     ProtoMessage
    -0.52
     Utt
    -0.51
    mapp
    -0.51
     InputDecoration
    -0.51
    POSITIVE LOGITS
     to
    0.64
     cappello
    0.57
     ImportError
    0.54
     igång
    0.51
    期刊论文
    0.51
    AppMethodBeat
    0.50
     rät
    0.50
    unknownFields
    0.50
     oeufs
    0.49
     kaybet
    0.49
    Activations Density 0.001%

    No Known Activations