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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92558
    Prev
    Next
    INDEX
    Explanations

    foo

    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
     ―――――
    -0.75
     Theſe
    -0.69
     myſelf
    -0.67
    ?—
    -0.64
     Efq
    -0.63
     itſelf
    -0.63
     ་་
    -0.61
     Anſ
    -0.61
     صوتيه
    -0.61
     (?
    -0.60
    POSITIVE LOGITS
    __':
    0.73
    ]")]
    0.65
     juridiques
    0.65
     AssemblyTitle
    0.59
    ManagedBean
    0.58
    PerformLayout
    0.56
    __":
    0.56
     motivadoras
    0.56
     passés
    0.56
    帖最后由
    0.55
    Activations Density 0.465%

    No Known Activations