© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95092
    Prev
    Next
    INDEX
    Explanations

    improvements

    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
    ########.
    -0.70
    sidemargin
    -0.69
     médicale
    -0.63
     végétale
    -0.62
    better
    -0.61
    GEBURTS
    -0.59
     Basis
    -0.59
     Prompt
    -0.59
     виправивши
    -0.58
    igshid
    -0.58
    POSITIVE LOGITS
     with
    0.79
     to
    0.77
     với
    0.56
     by
    0.54
     avec
    0.51
     WITH
    0.50
    stateParams
    0.47
     in
    0.47
     dengan
    0.45
    сюда
    0.45
    Activations Density 0.001%

    No Known Activations