© 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. 97541
    Prev
    Next
    INDEX
    Explanations

    purse frame

    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
     purse
    -0.74
    poptosis
    -0.66
    ed
    -0.65
     purses
    -0.64
    er
    -0.57
    ist
    -0.57
    frame
    -0.57
    Frame
    -0.55
     aikaa
    -0.55
    IsContent
    -0.54
    POSITIVE LOGITS
    djangoproject
    0.81
     pinulongan
    0.68
    VersionUID
    0.66
     AssemblyVersion
    0.62
    Vidite
    0.62
     getItemId
    0.60
    skid
    0.59
     виправивши
    0.57
    Bibliograf
    0.56
     Савезне
    0.54
    Activations Density 1.568%

    No Known Activations