© 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. 0-CLT-HP
    7. 45252
    Prev
    Next
    INDEX
    Explanations

    loss or removal

    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
     تانيه
    -0.82
     thither
    -0.82
     purpoſe
    -0.81
     Theſe
    -0.80
     Shakspeare
    -0.77
     Jefus
    -0.77
     devaluation
    -0.75
     ARXIV
    -0.75
     doInBackground
    -0.74
    ^(@)
    -0.74
    POSITIVE LOGITS
     transfieras
    0.48
    ary
    0.45
     out
    0.43
     force
    0.42
    ation
    0.42
    out
    0.42
    AnchorStyles
    0.41
     Дата
    0.41
     per
    0.40
     or
    0.40
    Activations Density 0.065%

    No Known Activations