© 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. 44096
    Prev
    Next
    INDEX
    Explanations

    News

    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
    numerusform
    -0.54
    einander
    -0.54
     Wikimedijinoj
    -0.51
     tasse
    -0.50
     more
    -0.49
     CreateTagHelper
    -0.47
    PrivateKey
    -0.47
     eerder
    -0.47
    WriteByte
    -0.47
     gesprochen
    -0.46
    POSITIVE LOGITS
     '\\;'
    0.73
    =$?
    0.71
    rungsseite
    0.64
    AddTagHelper
    0.63
    ⓧ
    0.62
    OCCURRED
    0.62
    ContentAsync
    0.59
    scriptcase
    0.57
    AutoScaleMode
    0.56
    UpInside
    0.56
    Activations Density 1.619%

    No Known Activations