© 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. 5-CLT-HP
    7. 95057
    Prev
    Next
    INDEX
    Explanations

    movement/changes of state

    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
     quæ
    -0.60
    Rcpp
    -0.50
     écl
    -0.50
     jspb
    -0.49
    aarrggbb
    -0.47
    verifyException
    -0.47
    Personensuche
    -0.47
     sebagai
    -0.45
     jako
    -0.43
    jsxFileName
    -0.43
    POSITIVE LOGITS
     further
    0.81
     along
    0.75
     through
    0.72
    HomeAsUpEnabled
    0.69
     deeper
    0.69
     farther
    0.66
     تانيه
    0.65
     throughout
    0.65
    ########.
    0.65
     from
    0.63
    Activations Density 0.001%

    No Known Activations