© 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. 93007
    Prev
    Next
    INDEX
    Explanations

    Related

    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
     الدولى
    -0.55
     HasFactory
    -0.47
    _));
    -0.47
     how
    -0.44
     regard
    -0.44
     preparedness
    -0.43
    stander
    -0.43
    UNUSED
    -0.43
     behalf
    -0.41
    rasında
    -0.41
    POSITIVE LOGITS
    TestingModule
    0.64
    libft
    0.64
    OGND
    0.62
    featureID
    0.59
    WebControls
    0.58
     nemlig
    0.56
    NameValuePair
    0.56
    gonic
    0.54
     InputDecoration
    0.54
     animasi
    0.53
    Activations Density 0.053%

    No Known Activations