© 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. 1176
    Prev
    Next
    INDEX
    Explanations

    to

    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
     questions
    -0.60
     Questions
    -0.51
     question
    -0.50
    ries
    -0.49
     Question
    -0.49
     Q
    -0.47
     qu
    -0.47
     QUESTIONS
    -0.47
    qu
    -0.45
    Question
    -0.45
    POSITIVE LOGITS
    windowFixed
    1.03
    AndEndTag
    0.85
    aarrggbb
    0.79
    ьаж
    0.75
    SourceChecksum
    0.69
     Roskov
    0.68
    featureID
    0.66
    Vidite
    0.65
    +#+#
    0.65
     SIMBAD
    0.64
    Activations Density 0.001%

    No Known Activations