© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9433
    Prev
    Next
    INDEX
    Explanations

    bility

    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
    cun
    -0.94
     aviator
    -0.59
     constexpr
    -0.57
     Normdatei
    -0.52
    toEqual
    -0.51
    andidaten
    -0.50
    furt
    -0.50
    circles
    -0.49
    zzard
    -0.49
    XQ
    -0.48
    POSITIVE LOGITS
     Roskov
    0.73
    Personendaten
    0.72
     lenker
    0.68
     تضيفلها
    0.68
    OGND
    0.68
    NewUrlParser
    0.67
    曖昧さ回避
    0.65
    ValueStyle
    0.63
    KURZBESCHREIBUNG
    0.62
    DockStyle
    0.62
    Activations Density 0.013%

    No Known Activations