© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93057
    Prev
    Next
    INDEX
    Explanations

    hips

    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
    AutoScaleMode
    -0.73
    lapsingToolbar
    -0.67
    writeFieldEnd
    -0.65
    fjspx
    -0.61
    PreferredItem
    -0.59
    AddTagHelper
    -0.53
    <bos>
    -0.50
    cookieParser
    -0.50
     Numerade
    -0.50
     GeoNames
    -0.49
    POSITIVE LOGITS
    grees
    0.54
    KURZBESCHREIBUNG
    0.52
    ragan
    0.51
    GEBURTS
    0.50
    PyExc
    0.50
    nefs
    0.48
     lot
    0.47
    umbres
    0.47
    ership
    0.47
    imanapun
    0.46
    Activations Density 0.005%

    No Known Activations